From the digital twins in healthcare to the Virtual Human Twin: a moon-shot project for digital health research

Marco Viceconti, Maarten De Vos, Sabato Mellone, Liesbet Geris

Introduction

Digital Twins in Healthcare (DTH) have demonstrated significant potential in specialized clinical applications, such as non-invasive coronary assessment. However, the field remains fragmented, characterized by isolated, single-scale models that lack interoperability. This position paper identifies seven systemic barriers—ranging from data scarcity and regulatory hurdles to a lack of specialized workforce—that prevent DTH from reaching its full potential. To address these, the authors propose a "moon-shot" project: the Virtual Human Twin (VHT), a distributed, collaborative ecosystem designed to unify data and models into a cohesive infrastructure.

The VHT Framework: A Multi-Dimensional Data Space

The VHT is not envisioned as a single monolithic model but as a distributed infrastructure built upon a 6D Data Space. This space organizes human pathophysiology data across six dimensions: Space (3D anatomical mapping), Time (lifespan or disease progression), Credibility (reliability scale from 0 to 1), and Clustering (grouping by demographics or health status).

Central to this architecture are Data Objects, which consist of a Data Object Type (DOT) and a Data Object Pose (DOP). The DOT defines the semantics, syntax, and accessibility of the data, while the DOP determines its specific coordinates within the 6D space.

Structure of Data Objects (DOT) and their Pose (DOP) within the VHT infrastructure.

This framework enables a "greedy" execution model where autonomous Model Objects (Data Space Crawlers) monitor the environment. When a model identifies a valid set of input data objects, it automatically executes and populates the space with new predicted data objects, creating a self-enriching knowledge base. Orchestration systems then link these single-scale models into complex multiscale workflows via standardized data flows.

Data Interoperability and Validation

A core pillar of the VHT is the transition from private, siloed validation to public, certified benchmark datasets. By adhering to FAIR principles (Findable, Accessible, Interoperable, Reusable), the VHT aims to provide a "digital agora" where researchers can independently validate models against curated data. This shift is essential for overcoming the current bottleneck where researchers validate their own models on non-public data, hindering objective comparison and regulatory approval.

Discussion and Future Directions

The VHT serves as the conceptual foundation for the EDITH initiative, a European roadmap for digital health research. By treating "Credibility" as a fundamental coordinate, the architecture integrates quality assurance directly into the data flow. However, significant challenges remain, particularly regarding GDPR-compliant data handling in distributed systems, the transition to sustainable business models, and the necessity of maintaining a "human-in-the-loop" for clinical safety.

Ultimately, the VHT represents a shift from viewing digital twins as individual products to viewing them as components of a larger, interconnected system that facilitates personalized healthcare at scale.

Summary updated

Abstract

The idea of a systematic digital representation of the entire known human pathophysiology, which we could call the Virtual Human Twin, has been around for decades. To date, most research groups focused instead on developing highly specialised, highly focused patient-specific models able to predict specific quantities of clinical relevance. While it has facilitated harvesting the low-hanging fruits, this narrow focus is, in the long run, leaving some significant challenges that slow the adoption of digital twins in healthcare. This position paper lays the conceptual foundations for developing the Virtual Human Twin (VHT). The VHT is intended as a distributed and collaborative infrastructure, a collection of technologies and resources (data, models) that enable it, and a collection of Standard Operating Procedures (SOP) that regulate its use. The VHT infrastructure aims to facilitate academic researchers, public organisations, and the biomedical industry in developing and validating new digital twins in healthcare solutions with the possibility of integrating multiple resources if required by the specific context of use. Healthcare professionals and patients can also use the VHT infrastructure for clinical decision support or personalised health forecasting. As the European Commission launched the EDITH coordination and support action to develop a roadmap for the development of the Virtual Human Twin, this position paper is intended as a starting point for the consensus process and a call to arms for all stakeholders.
BibTeX
@article{viceconti2024from,
  author = {Marco Viceconti and Maarten De Vos and Sabato Mellone and Liesbet Geris},
  title = {{From the digital twins in healthcare to the Virtual Human Twin: a moon-shot project for digital health research}},
  journal = {IEEE JBHI},
  year = {2024},
  doi = {10.1109/jbhi.2023.3323688},
}
Figure